sched/cache: Keep nr_pref_llc_running in the runnable domain, to fix LLC mis-scheduling buggrafted

alb_break_llc() decides whether to break LLC preference during active
load balance. It does so by testing that every runnable fair task on the
source rq prefers its LLC:

	env->src_rq->nr_pref_llc_running == env->src_rq->cfs.h_nr_runnable

But the two counters cover different sets. nr_pref_llc_running is updated
in account_llc_enqueue()/account_llc_dequeue(), next to cfs_rq->nr_queued,
so it follows queued tasks. h_nr_runnable is updated in set_delayed()/
clear_delayed() and drops delay-dequeued tasks.

So under DELAY_DEQUEUE, a preferring task that goes to sleep stays counted
in nr_pref_llc_running while h_nr_runnable falls. The equality then breaks,
alb_break_llc() returns false, and active balance is free to pull a task
off its preferred LLC. Active balance only moves runnable tasks, and this
is the only LLC check it consults: once the stopper runs, LBF_ACTIVE_LB
skips the per-task test in can_migrate_task(). The runnable set is the one
we want.

Fix it on the counter side. A task should be counted in
nr_pref_llc_running exactly while it is both queued on its preferred LLC
(pref_llc_queued) and runnable (!sched_delayed). Define that membership
once in task_pref_llc_runnable(), and adjust the counter only through
pref_llc_running_inc()/pref_llc_running_dec() from the four sites that
change either input: account_llc_enqueue(), account_llc_dequeue(),
set_delayed() and clear_delayed(). Gating every update on the same
predicate keeps the delay, wake and dequeue paths from double-counting
or underflowing; see the comments at those sites for the ordering.

nr_llc_running and sd->llc_counts are not touched and stay on queued
semantics.

Fixes: 714059f79ff0 ("sched/cache: Handle moving single tasks to/from their preferred LLC")
Closes: https://lore.kernel.org/lkml/20260827135000.735138-1-zhanxusheng@xiaomi.com/
Reported-by: Zhan Xusheng <zhanxusheng@xiaomi.com>
Suggested-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Kayra Cizmeci <kayracizmeci@gmail.com>
Cc: <stable@kernel.org> # v7.2.x
Link: https://patch.msgid.link/06af61afedac32e6477f57feb4d658f6c411c3af.1790035273.git.tim.c.chen@linux.intel.com

1 files changed, 94 insertions, 0 deletions

diff --git a/drivers/acpi/bgrt.c b/drivers/acpi/bgrt.c
new file mode 100644
index 000000000..0fdd581ef
--- /dev/null
+++ b/drivers/acpi/bgrt.c
@@ -0,0 +1,94 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * BGRT boot graphic support
+ * Authors: Matthew Garrett, Josh Triplett <josh@joshtriplett.org>
+ * Copyright 2012 Red Hat, Inc <mjg@redhat.com>
+ * Copyright 2012 Intel Corporation
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/device.h>
+#include <linux/sysfs.h>
+#include <linux/efi-bgrt.h>
+
+static void *bgrt_image;
+static struct kobject *bgrt_kobj;
+
+#define BGRT_SHOW(_name, _member) \
+	static ssize_t _name##_show(struct kobject *kobj,			\
+				    struct kobj_attribute *attr, char *buf)	\
+	{									\
+		return sysfs_emit(buf, "%d\n", bgrt_tab._member);		\
+	}									\
+	static struct kobj_attribute bgrt_attr_##_name = __ATTR_RO(_name)
+
+BGRT_SHOW(version, version);
+BGRT_SHOW(status, status);
+BGRT_SHOW(type, image_type);
+BGRT_SHOW(xoffset, image_offset_x);
+BGRT_SHOW(yoffset, image_offset_y);
+
+static __ro_after_init BIN_ATTR_SIMPLE_RO(image);
+
+static struct attribute *bgrt_attributes[] = {
+	&bgrt_attr_version.attr,
+	&bgrt_attr_status.attr,
+	&bgrt_attr_type.attr,
+	&bgrt_attr_xoffset.attr,
+	&bgrt_attr_yoffset.attr,
+	NULL,
+};
+
+static const struct bin_attribute *const bgrt_bin_attributes[] = {
+	&bin_attr_image,
+	NULL,
+};
+
+static const struct attribute_group bgrt_attribute_group = {
+	.attrs = bgrt_attributes,
+	.bin_attrs = bgrt_bin_attributes,
+};
+
+int __init acpi_parse_bgrt(struct acpi_table_header *table)
+{
+	efi_bgrt_init(table);
+	return 0;
+}
+
+static int __init bgrt_init(void)
+{
+	int ret;
+
+	if (!bgrt_tab.image_address)
+		return -ENODEV;
+
+	bgrt_image = memremap(bgrt_tab.image_address, bgrt_image_size,
+			      MEMREMAP_WB);
+	if (!bgrt_image) {
+		pr_notice("Ignoring BGRT: failed to map image memory\n");
+		return -ENOMEM;
+	}
+
+	bin_attr_image.private = bgrt_image;
+	bin_attr_image.size = bgrt_image_size;
+
+	bgrt_kobj = kobject_create_and_add("bgrt", acpi_kobj);
+	if (!bgrt_kobj) {
+		ret = -EINVAL;
+		goto out_memmap;
+	}
+
+	ret = sysfs_create_group(bgrt_kobj, &bgrt_attribute_group);
+	if (ret)
+		goto out_kobject;
+
+	return 0;
+
+out_kobject:
+	kobject_put(bgrt_kobj);
+out_memmap:
+	memunmap(bgrt_image);
+	return ret;
+}
+device_initcall(bgrt_init);